Hand and face landmark detection in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding landmark detection outputs

When a hand landmark detection model processes an image, what does its output typically represent?

A Coordinates of key points on the hand such as fingertips and joints

B A binary mask highlighting the hand region

C A classification label indicating hand gestures

D The raw pixel values of the hand area

💡 Hint

Think about what 'landmark' means in this context.

Landmark detection models output coordinates of specific points on the hand or face, like fingertips or facial features, to understand their positions.

❓ Predict Output

intermediate

Output shape of face landmark detection model

Given a face landmark detection model that detects 468 points per face, what is the shape of the output tensor for a batch of 5 images?

Computer Vision

batch_size = 5
num_landmarks = 468
output_shape = (batch_size, num_landmarks, 3)  # x, y, z coordinates

A (5, 3, 468)

B (5, 468, 3)

C (3, 468, 5)

D (468, 5, 3)

💡 Hint

Consider batch size first, then landmarks, then coordinates.

The output tensor shape is (batch_size, number_of_landmarks, coordinates_per_point). For 5 images and 468 landmarks with 3D coordinates, it is (5, 468, 3).

❓ Model Choice

advanced

Choosing a model for real-time hand landmark detection

You want to build a mobile app that detects hand landmarks in real-time video. Which model architecture is best suited?

A A deep transformer model with self-attention layers

B A large ResNet-based model with many layers for high accuracy

C A lightweight MobileNet-based model optimized for speed

D A simple linear regression model

💡 Hint

Think about balancing speed and accuracy on mobile devices.

MobileNet-based models are designed to be lightweight and fast, making them ideal for real-time applications on mobile devices.

❓ Metrics

advanced

Evaluating landmark detection accuracy

Which metric best measures the accuracy of predicted hand landmarks compared to ground truth points?

A Precision and recall of hand detection bounding boxes

B Classification accuracy of hand gesture labels

C Confusion matrix of detected vs missed landmarks

D Mean Squared Error (MSE) between predicted and true landmark coordinates

💡 Hint

Focus on how close predicted points are to actual points.

MSE measures the average squared distance between predicted and true landmark coordinates, quantifying prediction accuracy.

🔧 Debug

expert

Debugging inconsistent landmark predictions

You notice that your face landmark detection model sometimes predicts landmarks outside the face region. What is the most likely cause?

A The input images are not normalized or preprocessed consistently

B The model architecture is too deep

C The optimizer learning rate is too low

D The batch size during training was too large

💡 Hint

Think about input data quality and consistency.

If input images are not normalized or preprocessed consistently, the model may receive unexpected inputs causing incorrect landmark predictions outside the face.

Practice

1. What is the main purpose of hand and face landmark detection in computer vision?

easy

A. To compress video files

B. To increase image resolution

C. To change the color of images

D. To find key points on hands and faces in images or videos

Solution

1. Step 1: Understand the goal of landmark detection

   Landmark detection identifies important points on hands and faces to understand their shape and position.

2. Step 2: Compare options with the goal

   Only To find key points on hands and faces in images or videos matches this goal by describing key point detection on hands and faces.

3. Final Answer:

   To find key points on hands and faces in images or videos -> Option D

4. Quick Check:

   Landmark detection = key points detection [OK]

Hint: Landmark detection means finding important points [OK]

Common Mistakes:

• Confusing landmark detection with image enhancement
• Thinking it changes image colors
• Mixing it up with video compression

2. Which of the following is the correct way to import MediaPipe's hand landmark detection module in Python?

easy

A. import mediapipe.solutions.hands as mp_hands

B. import mediapipe.hands as mp_hands

C. import mediapipe as mp
mp.solutions.hands

D. from mediapipe import hands

Solution

1. Step 1: Recall MediaPipe import syntax

   MediaPipe modules are imported from mediapipe.solutions, e.g., mediapipe.solutions.hands.

2. Step 2: Check each option

   import mediapipe.solutions.hands as mp_hands correctly imports mediapipe.solutions.hands as mp_hands. Others are incorrect or incomplete.

3. Final Answer:

   import mediapipe.solutions.hands as mp_hands -> Option A

4. Quick Check:

   Correct import = mediapipe.solutions.hands [OK]

Hint: MediaPipe modules come from mediapipe.solutions [OK]

Common Mistakes:

• Using incorrect import paths
• Trying to import submodules directly without solutions
• Confusing alias names

3. Given the following Python code using MediaPipe for hand landmarks detection, what will be printed?

import mediapipe as mp
mp_hands = mp.solutions.hands
hands = mp_hands.Hands(static_image_mode=True)
results = hands.process(image_rgb)
print(len(results.multi_hand_landmarks))

Assuming image_rgb contains one clear hand.

medium

A. 1

B. Error

C. None

D. 0

Solution

1. Step 1: Understand the code flow

   The code processes an RGB image with one hand using MediaPipe Hands in static mode.

2. Step 2: Interpret the output

   Since one hand is present, results.multi_hand_landmarks will contain one set of landmarks, so its length is 1.

3. Final Answer:

   1 -> Option A

4. Quick Check:

   One hand detected = length 1 [OK]

Hint: Length of landmarks list equals number of detected hands [OK]

Common Mistakes:

• Assuming zero when hand is present
• Confusing None with empty list
• Expecting error without checking input

4. You wrote this code to detect face landmarks but get an error:

import mediapipe as mp
mp_face = mp.solutions.face_mesh
face_mesh = mp_face.FaceMesh()
results = face_mesh.process(image_bgr)
print(results.multi_face_landmarks)

What is the likely cause of the error?

medium

A. Missing import for cv2

B. FaceMesh class does not exist

C. Input image should be RGB, not BGR

D. process() method requires grayscale image

Solution

1. Step 1: Check input image format for MediaPipe FaceMesh

   MediaPipe expects RGB images, but the code uses image_bgr (BGR format).

2. Step 2: Understand error cause

   Using BGR instead of RGB causes wrong color channels and likely errors in detection.

3. Final Answer:

   Input image should be RGB, not BGR -> Option C

4. Quick Check:

   MediaPipe needs RGB input images [OK]

Hint: Always convert BGR to RGB before MediaPipe processing [OK]

Common Mistakes:

• Passing BGR images directly
• Assuming FaceMesh class is missing
• Thinking grayscale is required

5. You want to build a gesture recognition app using hand landmarks. Which approach best improves accuracy when hands are rotated or partially hidden?

hard

A. Only train on perfectly centered and clear hand images

B. Use data augmentation with rotated and occluded hand images during training

C. Ignore landmarks and use raw images directly

D. Use grayscale images instead of color

Solution

1. Step 1: Understand challenges in gesture recognition

   Hands can appear rotated or partly hidden, so model must handle variations.

2. Step 2: Choose best method to improve robustness

   Data augmentation with rotated and occluded images teaches model to recognize gestures despite changes.

3. Final Answer:

   Use data augmentation with rotated and occluded hand images during training -> Option B

4. Quick Check:

   Augmentation improves model robustness [OK]

Hint: Augment training data to handle rotations and occlusions [OK]

Common Mistakes:

• Training only on perfect images
• Ignoring landmarks reduces accuracy
• Using grayscale loses important info